Sensitive Detection of Cell-Free Tumour DNA Using Optimised Targeted Sequencing Can Predict Prognosis in Gastro-Oesophageal Cancer

Simple Summary Cancer in the stomach and oesophagus is deadly when discovered at a late stage. There are no good biomarkers for its detection or for making a prognostic prediction. In this study, we evaluate the analysis of cell-free DNA as a prognostic cancer biomarker. Cell-free DNA is DNA released from any tissue to a body fluid. When there is a tumour in the body, some of the cell-free DNA will come from that tumour, and it can be detected in a blood sample. We show that the detection of cell-free DNA from the cancer correlates to a worse prognosis than when no tumour DNA is detected. We also show that the method of analysis is important. Either a tissue biopsy must be included as a validation of the genetic variants detected or analysis of the blood cells or another blood sample after tumour resection needs to be analysed to improve detection. In this longitudinal study, cell-free tumour DNA (a liquid biopsy) from plasma was explored as a prognostic biomarker for gastro-oesophageal cancer. Both tumour-informed and tumour-agnostic approaches for plasma variant filtering were evaluated in 47 participants. This was possible through sequencing of DNA from tissue biopsies from all participants and cell-free DNA from plasma sampled before and after surgery (n = 42), as well as DNA from white blood cells (n = 21) using a custom gene panel with and without unique molecular identifiers (UMIs). A subset of the plasma samples (n = 12) was also assayed with targeted droplet digital PCR (ddPCR). In 17/31 (55%) diagnostic plasma samples, tissue-verified cancer-associated variants could be detected by the gene panel. In the tumour-agnostic approach, 26 participants (59%) had cancer-associated variants, and UMIs were necessary to filter the true variants from the technical artefacts. Additionally, clonal haematopoietic variants could be excluded using the matched white blood cells or follow-up plasma samples. ddPCR detected its targets in 10/12 (83%) and provided an ultra-sensitive method for follow-up. Detectable cancer-associated variants in plasma correlated to a shorter overall survival and shorter time to progression, with a significant correlation for the tumour-informed approaches. In summary, liquid biopsy gene panel sequencing using a tumour-agnostic approach can be applied to all patients regardless of the presence of a tissue biopsy, although this requires UMIs and the exclusion of clonal haematopoietic variants. However, if sequencing data from tumour biopsies are available, a tumour-informed approach improves the value of cell-free tumour DNA as a negative prognostic biomarker in gastro-oesophageal cancer patients.